xview3-kohei-solution

Usage

This repository assumes that the given data set is stored in the following locations:

$ ls data/input/xview3/*.csv
data/input/xview3/train.csv  data/input/xview3/validation.csv

$ ls data/input/xview3/downloaded
00a035722196ee86t.tar.gz  4455faa0cb4824f4t.tar.gz  85fe34d1aee53a7ft.tar.gz  c07f6ec980c2c149t.tar.gz
014261f774287442t.tar.gz  4518c556b38a5fa4t.tar.gz  864390795b0439b1t.tar.gz  c0831dbd6d7f3c56t.tar.gz
(snip)

In the case of training, create a virtual env as follows:

# Setup: Create the virtual env
$ poetry config virtualenvs.in-project true
$ poetry install
$ poetry run pip install albumentations timm segmentation_models_pytorch torch==1.10.0+cu113 torchvision==0.11.1+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html

Training

To save storage space, my preprocessing code assumes that the input image file is the original file in .tar.gz format. It does NOT assume pre-extracted files. The batch size and other settings are based on the assumption that two RTX3080 GPU cards are used.

$ bash train.sh

Inference

My containerized inference code follows the xView3 evaluation protocol. The detailed usage of the xview3 evaluation protocol is described in https://iuu.xview.us/verify.

To build the Docker Image, you need the model weights generated by train.sh. The pre-computed files can be downloaded from my Google Drive.

You will also need to download and extract gshhg-shp-2.3.7.zip as external data. GSHHG data can be found at https://www.ngdc.noaa.gov/mgg/shorelines/data/gshhg/latest/

The Docker image containing these model weights and external data has already been uploaded to Docker Hub (smly/kohei-xview3:latest).

## Setup: Build the docker image -----
$ docker build --no-cache -t kohei-xview3 .

## Inference -----
$ docker run \
    --shm-size 16G \
    --gpus=1 \
    --mount type=bind,source=/home/xv3data,target=/on-docker/xv3data \
    kohei-xview3 \
    /on-docker/xv3data/ \
    0157baf3866b2cf9v \
    /on-docker/xv3data/prediction/prediction.csv

Kohei's 5th place solution for xview3 challenge

Related tags

Overview

xview3-kohei-solution

Usage

Training

Inference

Owner

Kohei Ozaki

PyGCL: A PyTorch Library for Graph Contrastive Learning

CrossNorm and SelfNorm for Generalization under Distribution Shifts (ICCV 2021)

This is an official implementation for "Video Swin Transformers".

PyTorch implementation of paper: HPNet: Deep Primitive Segmentation Using Hybrid Representations.

The implementation of "Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer"

CVPR 2021 - Official code repository for the paper: On Self-Contact and Human Pose.

This is the official implementation of the paper "Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation".

[ICML 2021, Long Talk] Delving into Deep Imbalanced Regression

🔮 Execution time predictions for deep neural network training iterations across different GPUs.

Security evaluation module with onnx, pytorch, and SecML.

Face detection using deep learning.

Implementation of Perceiver, General Perception with Iterative Attention in TensorFlow

Axel - 3D printed robotic hands and they controll with Raspberry Pi and Arduino combo

Google-drive-to-sqlite - Create a SQLite database containing metadata from Google Drive

An auto discord account and token generator. Automatically verifies the phone number. Works without proxy. Bypasses captcha.

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

The official code for paper "R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling".

Code for paper "Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs"

FaceAPI: AI-powered Face Detection & Rotation Tracking, Face Description & Recognition, Age & Gender & Emotion Prediction for Browser and NodeJS using TensorFlow/JS

Pytorch implementation for "Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion" (NeurIPS 2021)